© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11039
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to personal and collective identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luster
    -0.67
    church
    -0.66
    aston
    -0.61
    whel
    -0.60
     Hague
    -0.57
    math
    -0.57
    vind
    -0.56
     Dram
    -0.55
     anytime
    -0.55
     guiActive
    -0.54
    POSITIVE LOGITS
     intend
    1.05
    're
    1.04
     mean
    1.02
     entail
    1.01
     meant
    0.99
    've
    0.98
    'd
    0.92
     ate
    0.92
     accomplished
    0.92
     perceive
    0.91
    Activations Density 0.116%

    No Known Activations